求助大神,非对角二元bekk(1,1)模型的估计,程序是在学习以及网上的搜素得出的,不知正确与否。
我的疑问是:
1.pmethod用simplex与BFGS的区别
2.Std Error / T-Stat / Signif 结果怎样判断好坏。
open data C:\Users\gorden\Desktop\high.xls
data(format=xls,org=columns) 1 252 s f
set rs = 100.0*log(s/s{1})
set rf = 100.0*log(f/f{1})
*VAR(1) model for the mean, BEKK for the variance
system(model=var1)
variables rs rf
lags 1
det constant
end(system)
garch(p=1,q=1,model=var1,mv=bekk,pmethod=simplex,piters=10,robust,hmatrices=hh,rvectors=rr) / rs rf
MV-GARCH, BEKK - Estimation by BFGS
Convergence in 73 Iterations. Final criterion was 0.0000000 <= 0.0000100
With Heteroscedasticity/Misspecification Adjusted Standard Errors
Usable Observations 249
Log Likelihood -549.91469203
Variable Coeff Std Error T-Stat Signif
*******************************************************************************
1. RS{1} -0.158827038 0.113779845 -1.39592 0.16273997
2. RF{1} 0.132704227 0.117758133 1.12692 0.25977547
3. Constant -0.021047042 0.089524559 -0.23510 0.81413269
4. RS{1} 0.187751597 0.131561626 1.42710 0.15355107
5. RF{1} -0.254972854 0.137684975 -1.85186 0.06404639
6. Constant -0.023355747 0.089562744 -0.26078 0.79426583
7. C(1,1) 1.064534050 0.273924879 3.88623 0.00010181
8. C(2,1) 0.944750970 0.324843279 2.90833 0.00363366
9. C(2,2) -0.000088703 0.011449139 -0.00775 0.99381839
10. A(1,1) -0.287018271 0.414065240 -0.69317 0.48820186
11. A(1,2) -0.403535040 0.423867882 -0.95203 0.34108165
12. A(2,1) 0.462739083 0.341129339 1.35649 0.17494281
13. A(2,2) 0.646847873 0.363369250 1.78014 0.07505317
14. B(1,1) 0.711469517 0.085849680 8.28739 0.00000000
15. B(1,2) -0.020874852 0.045466083 -0.45913 0.64614067
16. B(2,1) -0.016236134 0.177846631 -0.09129 0.92725986
17. B(2,2) 0.783354277 0.154850278 5.05879 0.00000042